Driving state monitoring system based on Kinect human body posture recognition

Abstract

The invention relates to a driving state monitoring and alarming system based on Kinect human body posture recognition. The system comprises a joint information acquisition unit, a driving posture processing unit and an alarming unit. The joint information acquisition unit is used for acquiring the body section image of a driver, obtaining the basic joint point positions of the human body according to an image recognition algorithm, binding joint point position data to a virtual skeleton model, establishing a space coordinate system and completing joint recognition. The driving posture processing unit is used for analyzing the virtual skeleton model of which joint recognition is completed, monitoring position information of all the joint points to obtain real-time movement information of the driver and comparing the position information of the joints with preset dangerous movement characteristic information, and transmitting a corresponding state abnormality signal to the alarming unit. The alarming unit is used for alarming after receiving the abnormality signal transmitted by the driving posture processing unit.

Description

technical field [0001] The invention relates to a driving state monitoring system, in particular to a driving state monitoring system based on Kinect human body posture recognition. Background technique [0002] Dangerous driving behavior is one of the culprits leading to frequent traffic accidents. How to effectively eliminate bad driving conditions and reduce drivers’ dangerous driving behaviors, especially intelligently monitor the driver’s posture, and give real-time warnings to dangerous driving behaviors. It is necessary to ensure driving safety. At present, there are many ways to realize the monitoring technology for dangerous driving, mainly including the following two categories: [0003] The first category is to place additional sensors in the clutch, brake pedal, engine and other positions in the car, for example: a car ECO driving state prompt system and prompt method (application number: 201410692465.8), a driving state detection system (application No.: 20131...

AI Technical Summary

Problems solved by technology

[0005] The first type of method relies on additional sensors placed inside the vehicle’s mechanical structure, which requires modification of the vehicle’s mechanical structure, which is costly and difficult, especially for vehicles that have already been put into use, requiring changes to their internal structures, which pose a risk Higher; the second type of method is greatly affected by environmental factors. The method of collecting driver images for analysis has strict requirements on ambient light, and cannot work normally on roads with poor lighting conditions. It is dependent on ambient light and cannot be applied to tunnels. , night and other low light conditions

Also, some methods of analyzing the driver's state by having the driver interact with the monitoring system can distract the driver and pose additional risks

Images